Page generation method and device, equipment and medium

Abstract

The embodiment of the invention provides a page generation method and device, equipment and a medium. A specific embodiment of the method comprises the steps of obtaining target information input by a user, and obtaining preliminary layout information of a target page for the target information through a generative language model; respectively obtaining internal structure information of each page component included in the preliminary layout information through a generative language model; in combination with the preliminary layout information and the internal structure information of each page component, obtaining target layout information corresponding to the target page; and according to the target layout information, performing page rendering through a page rendering engine to obtain a target page. Through the method, the processing or display page corresponding to the user input information can be automatically generated according to the user input information, and the working efficiency of the user is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of generative artificial intelligence technology, and in particular to a method, apparatus, device and medium for generating a page. Background Art

[0002] Existing application software usually displays information or provides operation interfaces to users through application pages. However, the page design of existing application software often tends to be complicated and comprehensive, making it difficult for users to easily find the specific page they want to view or operate, resulting in a gradual increase in user usage costs. It often takes a long time to explore or professional training to become proficient in using the software.

[0003] In order to improve user efficiency, a new method of generating pages is needed. Summary of the invention

[0004] The embodiments of the present disclosure describe a method, apparatus, device and medium for generating a page.

[0005] According to a first aspect, a method for generating a page is provided, comprising:

[0006] Obtain target information input by a user, and obtain preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and obtain internal structure information of each page component through the generative language model;

[0007] The target layout information corresponding to the target page is obtained by combining the preliminary layout information and the internal structure information of each page component; the page rendering engine is used to render the page according to the target layout information to obtain the target page.

[0008] According to a second aspect, there is provided an apparatus for generating a page, comprising:

[0009] The layout acquisition unit is configured to acquire target information input by a user, acquire preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and acquire internal structure information of each page component through the generative language model;

[0010] The comprehensive generation unit is configured to obtain target layout information corresponding to the target page by combining the preliminary layout information and the internal structure information of each page component; and to obtain the target page by performing page rendering through the page rendering engine according to the target layout information.

[0011] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method of the first aspect.

[0012] According to a fourth aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method of the first aspect is implemented.

[0013] According to an embodiment of the present disclosure, a method, device, equipment and medium for generating a page are provided. The target information input by the user can be obtained, and the preliminary layout information of the target page for the target information can be obtained through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page. And, through the generative language model, the internal structure information of each page component is obtained respectively. Then, the target layout information corresponding to the target page is obtained by combining the preliminary layout information and the internal structure information of each page component. And according to the target layout information, the page rendering is performed through a page rendering engine to obtain the target page. Through this method, an operation or data display page corresponding to the user input information can be automatically generated according to the user input information, thereby improving the user's work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram showing a method for generating a page according to an embodiment of the present disclosure is shown;

[0015] Figure 2 A schematic diagram showing a page structure according to an embodiment of the present disclosure;

[0016] Figure 3 A schematic diagram of a process of generating a page according to an embodiment of the present disclosure is shown;

[0017] Figure 4 A schematic diagram showing prompt information for selecting a component according to an embodiment of the present disclosure;

[0018] Figure 5 A schematic diagram showing prompt information for obtaining preliminary layout information according to an embodiment of the present disclosure;

[0019] Figure 6 A schematic diagram showing prompt information for obtaining internal structure information according to an embodiment of the present disclosure;

[0020] Figure 7 A schematic block diagram of a device for generating a page according to an embodiment of the present disclosure is shown;

[0021] Figure 8 A schematic diagram of the structure of an electronic device suitable for implementing an embodiment of the present disclosure is shown;

[0022] Fig. 9 A schematic diagram of the structure of a storage medium suitable for implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0023] The technical solution provided in this specification is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the inventions. It should also be noted that, for ease of description, only the parts related to the relevant inventions are shown in the accompanying drawings. It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0024] In the description of the implementations of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one / kind of implementation" or "the implementation" should be understood as "at least one / kind of implementation". The term "some implementations" should be understood as "at least some implementations". Other explicit and implicit definitions may also be included below.

[0025] As mentioned above, existing application software usually displays information to users or provides operation interfaces to users through application pages. However, the page design of existing application software often tends to be complicated and comprehensive, making it difficult for users to easily find the specific page they want to view or operate, resulting in a gradual increase in the cost of use for users. It often takes a long time to explore or professional training to be able to use the software proficiently. In addition, there are many functional components that can be called by application pages, and users often hope to quickly find functional components with high usability.

[0026] According to the existing conventional page design scheme, the pages in the application software usually have fixed functions and are in a specific link relationship with other pages included in the software, and the functional components included in the page are usually fixed. Therefore, the user needs to be familiar with the link relationship between different pages in the software and the functional components in each page before he can perform the desired operation. Therefore, according to the conventional page design scheme, it is difficult to solve the problem of allowing users to quickly access the pages they want to view or operate (for example, including functional components with high availability).

[0027] In order to solve the above technical problems, an embodiment of the present disclosure provides a method for generating a page. Figure 1 A schematic diagram of a method for generating a page according to an embodiment of the present disclosure is shown. Figure 1As shown, in some embodiments, target information input by the user in the form of, for example, natural language, description information of predetermined optional components of the page, and indication information of components (or simply page components) selected from the optional components of the page that constitute the target page for the target information can be combined and sent to a generative language model to obtain description information of the page components output by the generative language model. Then, the description information of the page components and indication information of the preliminary layout information of the generated page are sent to the generative language model to obtain preliminary layout information output by the generative language model, and the preliminary layout information may include component information of the page components based on a specific data format. Furthermore, indication information of generating internal structure information for each component can be sent to the generative language model to obtain internal structure information of each page component. For example, Figure 2 A schematic diagram of a page structure according to an embodiment of the present disclosure is shown. Figure 2In the example shown, for example, the preliminary layout information of page A may include component information of the page components constituting page A, such as the component information of the layout root node component (layout), the page header component (Header), the table component (Table), the chart component (Chart)... etc. The internal structure information of each page component may include the information of the page elements included in each page component, for example, the internal structure information of the table component may include the set of Columns of each column (Column) element included in the component. Thereafter, the target layout information corresponding to the target page may be obtained by combining the preliminary layout information and the internal structure information of each page component, and the page rendering is performed through the page rendering engine according to the target layout information to obtain the target page. The advantages of this method are: on the one hand, a target page corresponding to the semantics of the natural language information can be generated according to the natural language information input by the user, so that the user can access the page he wants to access in a highly concise manner, and the user's intention expressed in the natural language information can be completed through the page using the highly available page components, which greatly improves the user's work efficiency. Secondly, in the process of generating the target page, preliminary layout information and internal structure information of each page component are obtained from the generative language model in steps, and then the preliminary layout information and the internal structure information of each page component are combined to obtain the target layout information. This avoids the problem that in the process of obtaining layout information, the single output or output data volume of the generative language model is too large, exceeding its single access input or output threshold, and thus it is difficult to obtain complete layout information. Thirdly, in the process of generating the target page, by instructing the generative language model to select the constituent components of the target page (i.e., page components) from predetermined optional components accessible, such as those within or outside the enterprise, the scope of the page constituent components is reasonably restricted, reducing the possibility that the selected page components are unavailable components or inapplicable components, thereby improving the availability of the target page composed of page components.

[0028] The detailed process of this method is further described below.

[0029] Figure 3 FIG. 1 is a flow chart showing a method for generating a page according to an embodiment of the present disclosure. Figure 3 As shown, the method comprises at least the following steps:

[0030] Step S301, obtaining target information input by a user, and obtaining preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and obtaining internal structure information of each page component through a generative language model;

[0031] Step S303, combining the preliminary layout information and the internal structure information of each page component to obtain target layout information corresponding to the target page; and performing page rendering through a page rendering engine according to the target layout information to obtain the target page.

[0032] First, in step S301, the target information input by the user is obtained, and preliminary layout information of the target page for the target information is obtained through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and the internal structure information of each page component is obtained respectively through the generative language model.

[0033] A generative language model may be a neural network model based on natural language processing that can be used for text generation, and may generate grammatically compliant, natural, and fluent text output based on input text content in natural language form. In different embodiments, different specific types of generative language models may be used, and this specification does not limit this. Since a generative language model may perform text input for natural language information, in one embodiment, the target information input by the user may be natural language information.

[0034] In different embodiments, the target information input by the user may be different specific information, and the intentions expressed by the user through the input target information may also be different specific intentions, and this specification does not limit this. For example, in one example, the user wants to submit a leave application, and can enter the natural language "leave approval". In another example, the user wants to display the work progress, and can enter the natural language "generate a weekly report for the last week". The target page may be a page generated according to the intentions expressed by the user through the target information. In different embodiments, the generated target page may also be different according to the different intentions expressed by the user through the target information.

[0035] In different embodiments, the specific method of obtaining the preliminary layout information of the target page for the target information through the generative language model may be different. In one embodiment, the target information, the description information for the predetermined multiple optional components, and the first indication information for indicating the determination of the page components from the optional components may be input into the generative language model to obtain the output of each page component determined from the multiple optional components. Then, the target information, the description information for each page component, and the second indication information for indicating the generation of the preliminary layout information may be input into the generative language model to obtain the output preliminary layout information. Figure 4 FIG. 1 is a schematic diagram showing prompt information for selecting a component according to an embodiment of the present disclosure. Figure 4In the example shown, for example, description information of the optional components and indication information (first indication information) for determining page components from the optional components may be sent to the generative language model. Figure 5 A schematic diagram of prompt information for obtaining preliminary layout information according to an embodiment of the present disclosure is shown. Figure 5 In the example shown, for example, description information of the page components determined and instruction information (second instruction information) for generating preliminary layout information may be sent to the generative language model.

[0036] In different specific embodiments, the optional components include one or more of a user interface (UI) component for displaying a user interface, a data component for providing data, a logic component for performing logic processing, and the like. In different specific embodiments, the optional components may be, for example, internal components of an enterprise, or may be accessible external components. In a specific embodiment, the description information for a predetermined plurality of optional components may include the names of the optional components and / or functional descriptions of the optional components. According to the above method, the constituent components of a page are determined from pre-integrated optional components (e.g., optional components accessible inside or outside the enterprise), and the scope of the constituent components of the page can be reasonably restricted, thereby reducing the possibility that the selected page components are unavailable components or inappropriate components.

[0037] In one embodiment, the first indication information may also include indication information of a data format Schema (for example, a first data format) associated with the description information of each page component output by the generative language model. Thus, the description information of each page component output based on the first data format can be obtained from the generative language model. In the above manner, the output data format (Schema) is indicated to the generative language model, which facilitates constraining the output result of the generative language model so that it conforms to the expected data format and facilitates subsequent data processing. In a specific embodiment, the first data format may also be represented by information of an interface (Interface) based on a predetermined programming language (for example, first interface information). Furthermore, the first indication information may also include the first interface information, such as Figure 4 As shown. In different specific embodiments, the predetermined programming language can be a different specific programming language. The information representation data format of the interface of the predetermined programming language requires a shorter text length than the conventional Schame representation (for example, represented by the Jason format), and the generative language model can also understand and process it. Therefore, the amount of data input into the generative model can be further reduced, thereby further reducing the possibility of a single input to the generative language model exceeding its input threshold, and the cost of using the generative language model can be reduced.

[0038] In the actual production process, the output results of the generative language model are often mixed with information other than the expected results (such as the description information of the page components determined from the optional components). Therefore, in order to facilitate the extraction of the expected results from the output results of the generative language model, in a specific embodiment, the first indication information may also include the packaging method of the description information of each page component output by the generative language model, and / or example information of the packaging method. In different specific embodiments, the packaging method may be different specific packaging methods. For example, Figure 4 In the example shown, the specific encapsulation method may be to use JSON-UIDL["..."]JSON-UIDL to encapsulate the returned description information of each page component.

[0039] The specific method of obtaining the internal structure information of each page component may also be different in different embodiments. In one embodiment, the internal structure information of each page component may be obtained in the following manner: for each page component, the target information, the preliminary layout information, and the third indication information for indicating the generation of the internal structure information of the page component are input into the generative language model, such as Figure 6 As shown. The internal structure information of the output page component is obtained. In the above manner, the internal structure information of each page component is obtained from the generative language model respectively. It can avoid that the single output or output data volume of the generative language model is too large, exceeding the input or output threshold of its single access.

[0040] Similar to the first indication information, the second indication information and the third indication information may also include one or more of the data format information represented by the interface information, the packaging method of the expected information, and the packaging example, for example Figure 5 , Figure 6 As shown, its function is similar to the same type of information included in the first indication information, and will not be repeated here. Since the data formats associated with different page components may be different. Therefore, in one embodiment, for each page component, the second data format associated with the page component can be obtained, and the second data format is represented by the second interface information based on a predetermined programming language. Furthermore, the second interface information can be included in the third indication information.

[0041] Then, in step S303, the target layout information corresponding to the target page is obtained by combining the preliminary layout information and the internal structure information of each page component; and the page rendering engine is used to render the page according to the target layout information to obtain the target page.

[0042] In this step, the preliminary layout information obtained in step S301 and the internal structure information of each page component can be combined to obtain the complete layout information corresponding to the target page, that is, the target layout information. In different embodiments, the target layout information obtained by combining can be different for different target information input by the user. In one embodiment, in order to facilitate subsequent page rendering, the target layout information can be based on the layout information of a predetermined user interface definition language (Interface Definition Language, IDL). In different embodiments, the predetermined user interface definition language can be different, and this specification does not limit this. In order to facilitate the combination of target layout information, in one embodiment, in the indication information (such as the second indication information) for generating preliminary layout information sent to the generative language model in step S301, the data format of the indicated preliminary layout information can be based on the data format of the predetermined user interface definition language. Similarly, in the indication information (such as the third indication information) for generating the internal structure information of each page component sent to the generative language model, the data format of the indicated internal structure information can also be based on the data format of the predetermined user interface definition language.

[0043] After obtaining the target layout information, the page rendering can be performed by a page rendering engine according to the target layout information to obtain the target page. In different embodiments, the specific page rendering engine used for page rendering can be different, and this specification does not limit this.

[0044] In one embodiment, after step S303, the target page can also be displayed to the user. In different embodiments, according to the different intentions expressed by the user input information (target information) obtained in step S301, the target page can be used, for example, for the user to perform the desired operation through the target page, or to display the desired data to the user. In another example, if the user wants to submit a leave, he can enter the natural language "leave approval". The target page can display the components of the leave process and the components for submitting leave, so that the user can view the leave process and submit the leave request through the target page. In another example, if the user wants to show the work progress, he can enter the natural language "generate a weekly report for the last week". Then the data or logical components associated with the weekly report can be determined, the weekly report data can be queried through the data or logical components, and the query results can be displayed, for example, through a table component. In the above manner, a target page corresponding to the semantics of the natural language information can be generated according to the natural language information input by the user, so that the user can access the page he wants to access in a highly concise manner, and the user's intention expressed in the natural language information can be completed through the page using a highly available page component, which greatly improves the user's work efficiency.

[0045] Figure 7 A schematic block diagram of a device for generating a page according to an embodiment of the present disclosure is shown. The device is used to perform the following steps: Figure 3 The method shown, such as Figure 7 As shown, the device 700 includes:

[0046] The acquisition unit 701 is configured to acquire target information input by a user, acquire preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and acquire internal structure information of each page component through a generative language model;

[0047] The generating unit 702 is configured to obtain target layout information corresponding to the target page by combining the preliminary layout information and the internal structure information of each page component; and perform page rendering through a page rendering engine according to the target layout information to obtain the target page.

[0048] The present disclosure also provides an electronic device, including a memory and a processor. The memory stores executable code. When the processor executes the executable code, the following is achieved: Figure 3 The method shown.

[0049] You can also refer to the following Figure 8 , which shows a structural schematic diagram of an electronic device 800 suitable for implementing an embodiment of the present application. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0050] like Figure 8As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801. The above-mentioned processing device 801 may be a general-purpose processor, a digital signal processor (Digital Signal Processing, DSP), a microprocessor or a microcontroller, and may further include an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage device 808 to the random access memory (RAM) 803. In RAM803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, ROM802 and RAM803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0051] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 8 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0052] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method for generating a page provided in the embodiment of the present application are executed.

[0053] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the following steps provided in the present disclosure: Figure 3 The method of generating the page shown in . Fig. 9 A schematic diagram of a storage medium for implementing an embodiment of the present application. Fig. 9 As shown, the storage medium 900 may be a non-transitory computer-readable storage medium for storing non-transitory computer-executable instructions 901. When the non-transitory computer-executable instructions 901 are executed by the processor, the method for generating a page provided in the embodiment of the present application may be implemented. For example, when the non-transitory computer-executable instructions 901 are executed by the processor, one or more steps in the method for generating a page provided in the embodiment of the present application may be executed. For example, the storage medium 900 may be applied to the above-mentioned electronic device. For example, the storage medium 900 may include a memory in the electronic device. For the description of the storage medium 900, reference may be made to the description of the memory in the embodiment of the electronic device, and the repetitive parts will not be repeated. The specific functions and technical effects of the storage medium 900 may refer to the description of the method for generating a page provided in the embodiment of the present application, and will not be repeated here.

[0054] It should be noted that the computer-readable medium of the embodiment of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a memory card of a smart phone, a storage component of a tablet computer, a portable computer disk, a hard disk of a personal computer, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0055] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the server, the electronic device implements the method for generating a page provided in the embodiment of the present application.

[0056] Computer program code for performing the operations of the disclosed embodiments may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0057] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions. The units involved in the embodiments described in the present disclosure can be implemented by software or by hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances. The functions described above in this article can be performed at least in part by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0058] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the storage medium and computing device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0059] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned public concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) to form a technical solution. In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of a single embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0060] The above specific implementation methods further describe in detail the purpose, technical solutions and beneficial effects of the embodiments of the present invention. Although the subject matter has been described in a language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. It should be understood that the above are only specific implementation methods of the embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a page, comprising: Obtain target information input by a user, and obtain preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and obtain internal structure information of each page component through the generative language model; Combining the preliminary layout information and the internal structure information of each page component, obtaining the target layout information corresponding to the target page; According to the target layout information, the page is rendered through the page rendering engine to obtain the target page.

2. The method according to claim 1, wherein Through the generative language model, the preliminary layout information of the target page for the target information is obtained, including: Inputting the target information, description information of the predetermined plurality of optional components, and first indication information for indicating that a page component is determined from the optional components into a generative language model, and obtaining output of each page component determined from the plurality of optional components; The target information, the description information for each page component and the second instruction information for instructing to generate the preliminary layout information are input into the generative language model to obtain the output preliminary layout information.

3. The method according to claim 2, wherein: Through the generative language model, the internal structure information of each page component is obtained, including: For each page component, the target information, the preliminary layout information, and the third indication information for indicating the generation of the internal structure information of the page component are input into the generative language model to obtain the output internal structure information of the page component.

4. The method according to claim 2, wherein: The first indication information also includes: Indicative information in a first data format associated with description information of each page component output by the generative language model; The output page components are determined from multiple optional components, including: The output description information of each page component based on the first data format is obtained.

5. The method according to claim 4, further comprising: Representing the first data format through first interface information based on a predetermined programming language; The first indication information includes the first interface information.

6. The method according to claim 2, wherein: The first indication information also includes: The encapsulation method of the description information of each page component output by the generative language model and / or example information of the encapsulation method.

7. The method according to claim 3, further comprising: Acquire a second data format associated with the page component, and represent the second data format through second interface information based on a predetermined programming language; The third indication information includes the second interface information.

8. The method according to claim 2, wherein: The description information of the predetermined plurality of optional components includes the names of the optional components and / or functional descriptions of the optional components.

9. The method according to claim 1 further comprises presenting the target page to a user.

10. The method according to claim 1, wherein: The target information is natural language information.

11. A device for generating a page, comprising: The acquisition unit is configured to acquire target information input by a user, acquire preliminary layout information of a target page for the target information through a generative language model, wherein the preliminary layout information includes component information of multiple page components constituting the target page; and acquire internal structure information of each page component through the generative language model; The generating unit is configured to obtain target layout information corresponding to the target page by combining the preliminary layout information and the internal structure information of each page component; According to the target layout information, the page is rendered through the page rendering engine to obtain the target page.

12. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 10.

13. An electronic device comprising a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 10 is implemented.

Images